AI Agent Skills

[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrai…

Golang everyday observability — the always-on signals in production. Covers structured logging with slog, Prometheus metrics, OpenTelemetry distributed tracing, continuo…

Golang benchmarking, profiling, and performance measurement. Use when writing, running, or comparing Go benchmarks, profiling hot paths with pprof, interpreting CPU/memo…

Autonomous AI pentesting engine performing continuous offensive security across web, cloud, AD and Kubernetes. Uses agentic reasoning, real exploit execution and attack…

High-performance analytical database. 19.9M records/sec ingestion, 8.4M+ rows/sec queries. Ingestion, compaction, SQL, retention, continuous queries — one binary. Open P…

Jenkins shared library for Continuous Delivery pipelines.

Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.

Use this skill to manage the full lifecycle of a DevOps Center pipeline — list all pipelines, get a single pipeline's details, create a new pipeline linked to a Git repo…

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine w…

Suite of human-collected datasets and a multi-task continuous control benchmark for open vocabulary visuolinguomotor learning.

InfraBox is a cloud native continuous integration system

[ICLR 2025] "Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances" (Official Implementation)

This repository contains rules for continuous, GitOps driven Kubernetes deployments.

🦄 Unitxt is a Python library for enterprise-grade evaluation of AI performance, offering the world's largest catalog of tools and data for end-to-end AI benchmarking

Co-creation infrastructure for humans and code agents — visual environment, skills, continuous learning, and distribution.

Turn isolated Claude sessions into a continuous working relationship